Retrieval Augmented Generation (RAG) implementation

[ericphann]

• Identify and integrate a suitable data source (e.g., CSV file, text corpus) for RAG
• Implement a basic RAG process using libraries like LangChain or similar tools
• One option, provide a Jupyter notebook demonstrating the RAG process (easier option)
• Ideally, integrate RAG directly into the application (e.g., via Streamlit)
• Consider these repos: https://github.com/NirDiamant/RAG_Techniques/tree/main

[ericphann]

Merged pull request #10.

• Data source is synthetic data from Anthropic.
• RAG developed using OpenAI and FAISS.
• Streamlit integration will come in a future enchancement